Objective: The identification method used in this study is a backpropagation artificial neural network. By using local threshold image processing then the image is extracted features with angular second moment (ASM), Entropy, Correlation, Contrast, and IDM. After the training and testing process using backpropagation ANN momentum can be implemented in the application design for the identification of symptoms of hypertension. The materials used in this study were 196 eye images consisting of training data used in this study as many as 140 images and test data as many as 56 iris image data. For the data collection process that has been separated between the hypertensive eye image and the normal eye image, then the data is processed to determine whether the data is accurate or not. After the iris image data is collected, the next step is pre-processing. In this stage, there are several processes including Cropping, RGB to Greyscale, Feature Extraction, and Experiments. Methods: The best accuracy results were obtained using a parameter with a value of Learning Rate = 0.1 in the 100th iteration with the highest percentage of 89.28% occurring in the training data, while the highest test data was 87.50%. Results: Based on the accuracy value obtained, the classification results obtained are in a fairly good category. Conclusions: Objective: High blood pressure or hypertension is a disorder of the blood vessels and heart that results in the supply of oxygen and nutrients being carried by the blood late to the body's tissues. Continuous high blood pressure causes the heart to work hard, resulting in damage to the blood vessels of the heart, brain, and eyes. The purpose of this study is to create an identification system that can identify symptoms of hypertension based on the iris of the eye using an artificial neural network algorithm with the backpropagation method. Methods: The identification method used in this study is a backpropagation artificial neural network. By using local threshold image processing then the image is extracted features with angular second moment (ASM), Entropy, Correlation, Contrast, and IDM. After the training and testing process using backpropagation ANN momentum can be implemented in the application design for the identification of symptoms of hypertension. The materials used in this study were 196 eye images consisting of training data used in this study as many as 140 images and test data as many as 56 iris image data. For the data collection process that has been separated between the hypertensive eye image and the normal eye image, then the data is processed to determine whether the data is accurate or not. After the iris image data is collected, the next step is pre-processing. In this stage, there are several processes including Cropping, RGB to Greyscale, Feature Extraction, and Experiments. Results: The best accuracy results were obtained using a parameter with a value of Learning Rate = 0.1 in the 100th iteration with the highest percentage of 89.28% occurring in the training data, while the highest test data was 87.50%. Conclusions: Based on the accuracy value obtained, the classification results obtained are in a fairly good category.